INDEX

Explanations

names of specific places, organizations, and positions

oai_token-act-pair · gpt-3.5-turbo

proper nouns and entities related to institutions, events, and locations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rab

-0.86

nec

-0.84

uggest

-0.82

vag

-0.79

alien

-0.79

wal

-0.77

hex

-0.77

seeing

-0.73

quant

-0.73

rongh

-0.73

POSITIVE LOGITS

 Industries

1.13

 Networks

1.12

 Records

1.08

 Enterprises

1.07

 Publications

1.06

 Studios

1.06

 Settlement

1.05

 Ventures

1.05

 Market

1.03

 Airways

1.03

Activations Density 0.212%

names of specific places, organizations, and positions

proper nouns and entities related to institutions, events, and locations

No Comments

No Known Activations